Novel Hybrid Adaptive Controller for Manipulation in Complex Perturbation Environments
- Submitting institution
-
University of Plymouth
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 2068
- Type
- D - Journal article
- DOI
-
10.1371/journal.pone.0129281
- Title of journal
- PLoS One
- Article number
- e0129281
- First page
- -
- Volume
- 10
- Issue
- 6
- ISSN
- 1932-6203
- Open access status
- Out of scope for open access requirements
- Month of publication
- June
- Year of publication
- 2015
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
5
- Research group(s)
-
-
- Citation count
- 35
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This work presents two innovative methods for the design of controllers for robot manipulation: A hybrid, human-like controller that minimises, both, control effort and tracking error, leading to a significant supra-linear boost in the correction of disturbances; and an online adaptation of learning parameters, that allows to avoid extensive trial testing, to integrate expert knowledge, and to further improve the controller performance. The work is especially important, because both methods can be easily generalised to other robot applications and domains.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -